3 papers
cs.CV2026
MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training
Qinyue Tong, Xiaozhen Wang, Ziqian Lu +3
Despite recent progress in text-prompt-based medical image segmentation, existing LISA-like MLLM-based methods typically generate masks regardless of whether the target specified i…
cs.CV2026
A Survey of Multimodal Hallucination Evaluation and Detection
Zhiyuan Chen, Yuecong Min, Jie Zhang +4
Multi-modal Large Language Models (MLLMs) have emerged as a powerful paradigm for integrating visual and textual information, supporting a wide range of multi-modal tasks. However,…
cs.CV2025
SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs
Bei Yan, Zhiyuan Chen, Yuecong Min +4
Despite rapid advances, Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge, whic…